{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UUI7464NP7SIJQ3YN7YO45DTHS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"277f26dd1a848ea4a116f2899c2b9e398fb6f77919c7015687666c1a731a1745","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T06:13:51Z","title_canon_sha256":"46b786613518f3dd495fde55993eef2c5f23cb331977f7da9441d92ce8a9dac8"},"schema_version":"1.0","source":{"id":"2302.11793","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11793","created_at":"2026-07-05T06:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11793v2","created_at":"2026-07-05T06:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11793","created_at":"2026-07-05T06:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"UUI7464NP7SI","created_at":"2026-07-05T06:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"UUI7464NP7SIJQ3Y","created_at":"2026-07-05T06:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"UUI7464N","created_at":"2026-07-05T06:20:41Z"}],"graph_snapshots":[{"event_id":"sha256:82714a2bb36f7324a18c2c24d2011586ee3130ee111274c86b2de5167a5067b8","target":"graph","created_at":"2026-07-05T06:20:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.11793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"MADDPG is an algorithm in multi-agent reinforcement learning (MARL) that extends the popular single-agent method, DDPG, to multi-agent scenarios. Importantly, DDPG is an algorithm designed for continuous action spaces, where the gradient of the state-action value function exists. For this algorithm to work in discrete action spaces, discrete gradient estimation must be performed. For MADDPG, the Gumbel-Softmax (GS) estimator is used -- a reparameterisation which relaxes a discrete distribution into a similar continuous one. This method, however, is statistically biased, and a recent MARL bench","authors_text":"Callum Rhys Tilbury, Filippos Christianos, Stefano V. Albrecht","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T06:13:51Z","title":"Revisiting the Gumbel-Softmax in MADDPG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11793","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e6d72ba94eaf2118404c1857dd3fa3cefa6895105873185ad64f2b052338e9eb","target":"record","created_at":"2026-07-05T06:20:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"277f26dd1a848ea4a116f2899c2b9e398fb6f77919c7015687666c1a731a1745","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T06:13:51Z","title_canon_sha256":"46b786613518f3dd495fde55993eef2c5f23cb331977f7da9441d92ce8a9dac8"},"schema_version":"1.0","source":{"id":"2302.11793","kind":"arxiv","version":2}},"canonical_sha256":"a511fe7b8d7fe484c3786ff0ee74733c9d97f7217333d7a84aea7b488f7443bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a511fe7b8d7fe484c3786ff0ee74733c9d97f7217333d7a84aea7b488f7443bc","first_computed_at":"2026-07-05T06:20:41.006945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:41.006945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AHD3kUO5oSrDxwIgqMTp4g/LPTgrvPbnRI+JVBMhkbSX4EypjIcZRxbav3llTCEJoXAy6MnhVMo5tHVhgVb2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:41.007357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.11793","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6d72ba94eaf2118404c1857dd3fa3cefa6895105873185ad64f2b052338e9eb","sha256:82714a2bb36f7324a18c2c24d2011586ee3130ee111274c86b2de5167a5067b8"],"state_sha256":"f5b3a0ce9e75746d903b12f837247cf7b526371b6b6f2f5079144e58d1ba352a"}